| 115 | 0 | 2 |
| Downloads | Citas | Reads |
该实验基于粒子群优化算法（PSO）对BP神经网络进行改进，利用BTS充放电测试仪对锂电池进行加速老化实验，从电池历史老化数据中提取健康因子，将其作为PSO-BP网络的输入，提高网络预测电池剩余使用寿命能力，最后利用多组电池的老化数据将传统预测算法与优化的PSO-BP网络的预测精确度进行了对比。针对PSO算法易陷入局部最优陷阱与早熟收敛问题，选择非线性动态自适应惯性权重策略（IPSO）对算法再次进行改进，通过对比改进前后算法的预测效果，验证得出IPSO-BP算法更加优异。该实验过程可以使学生利用机器学习算法预测电池剩余使用寿命，采用虚实结合手段解决实际问题，提高实验的综合效果。
Abstract：[Objective] The battery management system plays a crucial role in the new energy vehicle industry and battery chemical processes. Predicting battery remaining useful life(RUL) significantly impacts the efficiency and accuracy of this system. However, batteries exhibit complex chemical mechanisms and physical changes, making it essential to study battery parameter characteristics deeply and develop effective life prediction models. While traditional prediction algorithms can estimate battery life, their accuracy is often insufficient. This paper designs a neural network prediction algorithm combining nonlinear dynamic adaptive inertia weight with twice particle swarm optimization(IPSO-BP) to significantly improve prediction accuracy. [Methods] This paper investigates data extraction and prediction algorithms for lithium battery RUL. First, the LAN BTS battery tester and electrochemical workstation were used to conduct charge-discharge tests and complete cycle accelerated aging tests on multiple lithium battery groups. The test data were preprocessed and saved. Then, the BP neural network was improved based on the particle swarm optimization algorithm(PSO). Health factors extracted from the battery's historical aging data served as input to the PSO-BP network to train its prediction capability. Multiple sets of battery aging data were used for prediction calculations, comparing traditional algorithms with the PSO-BP network to identify a higher-accuracy approach. Subsequently, to address the PSO algorithm's tendency to fall into local optima and premature convergence, a nonlinear dynamic adaptive inertia weight strategy was implemented, resulting in the improved IPSO-BP algorithm. Finally, new degradation datasets were measured using the battery tester, imported into the IPSO-BP model, and the RUL prediction curve was generated and compared against the actual test curve. [Results] Comparing the prediction results of different algorithms verified the superiority of the proposed approach. The same experimental data were predicted using SVM, RF, BP, and PSO-BP algorithms. The PSO-BP algorithm achieved the smallest mean square error(approximately 0.011), meeting RUL prediction requirements but not being optimal. The developed IPSO-BP model was then compared against PSO-BP. The IPSO-BP algorithm demonstrated significantly better prediction accuracy and a trend closer to the real values than PSO-BP. [Conclusions] This paper innovatively designs a combined virtual and physical experimental process for lithium battery life prediction and constructs an IPSO-BP prediction algorithm. Comparing battery accelerated aging test results with simulation calculations revealed that this algorithm not only outperforms traditional algorithms but also aligns more closely with real test values. This experimental design provides students with a robust platform, enhancing their practical abilities in data testing, processing, computational model development, and result prediction, while broadening their engineering problem-solving skills.
[1]鲁源博,侯永平,焦道宽,等.燃料电池预测模型输出结果统计分析[J].电池, 2024, 54(6):772–776.LU Y B, HOU Y P, JIAO D K, et al. Statistical analysis of the output results of fuel cell prediction model[J]. Battery Bimonthly, 2024, 54(6):772–776.(in Chinese)
[2]张宇波,王有元,黄洞宁,等.面向变工况条件的锂离子电池寿命退化预测方法[J].储能科学与技术, 2023, 12(7):2238–2245.ZHANG Y B, WANG Y Y, HUANG D N, et al. Prognostic method of lithium-ion battery lifetime degradation under various working conditions[J]. Energy Storage Science and Technology, 2023, 12(7):2238–2245.(in Chinese)
[3]李成,陈球,于莹莹,等.基于IWOA-LSSVM的锂离子电池RUL预测[J].电气工程学报, 2024, 19(3):399–411.LI C, CHEN Q, YU Y Y, et al. Remaining useful life prediction for lithium-ion batteries based on IWOA-LSSVM[J]. Journal of Electrical Engineering, 2024, 19(3):399–411.(in Chinese)
[4]叶鑫,王海瑞,李远博,等.基于VMD和优化的LSTM锂离子电池寿命预测方法[J].电子测量技术, 2022, 45(23):153–158.YE X, WANG H R, LI Y B, et al. Remaining useful life prediction method of lithium-ion battery based on variational mode decomposition and optimized lstm[J]. Electronic Measurement Technology, 2022, 45(23):153–158.(in Chinese)
[5]高静怡,陈首轩,周明博,等.充放电多特征融合的锂电池寿命预测方法[J].重庆理工大学学报(自然科学), 2023,37(2):28–37.GAO J Y, CHEN S X, ZHOU M B, et al. Remaining useful life prediction method of a lithium-ion battery based on multi-feature fusion of charging and discharging[J]. Journal of Chongqing Institute of Technology(Natural Science), 2023,37(2):28–37.(in Chinese)
[6]赵波,张领先,章雷其,等. PEMFC剩余使用寿命直接预测的混合方法[J].中国电机工程学报, 2024, 44(21):8554–8568.ZHAO B, ZHANG L X, ZHANG L Q, et al. A hybrid method for direct prediction of PEMFC remaining useful life[J].Proceedings of the CSEE, 2024, 44(21):8554–8568.(in Chinese)
[7]李练兵,朱乐,李思佳,等.基于差分电压和ICS-Elman神经网络的锂离子电池剩余使用寿命预测方法[J].太阳能学报,2023, 44(12):433–443.LI L B, ZHU L, LI S J, et al. Remaining useful life prediction of lithium-ion batteries based on differential voltage and ICS-Elman neural networks[J]. Acta Energiae Solaris Sinica,2023, 44(12):433–443.(in Chinese)
[8]侯小康,袁裕鹏,童亮.基于改进相关向量机的锂电池剩余使用寿命预测[J].电源技术, 2024, 48(2):289–298.HOU X K, YUAN Y P, TONG L. Remaining useful life prediction of li-ion batteries based on improved relevance vector machine[J]. Chinese Journal of Power Sources, 2024,48(2):289–298.(in Chinese)
[9]夏向阳,吕崇耿,吴小忠,等.基于混合模型的储能用锂离子电池剩余寿命预测方法研究[J].太阳能学报, 2024, 45(10):726–735.XIA X Y, LYU C G, WU X Z, et al. Research on remaining life prediction method of lithium-ion battery for energy storage based on hybrid model[J]. Acta Energiae Solaris Sinica, 2024,45(10):726–735.(in Chinese)
[10]蔡雨思,李泽文,刘萍,等.基于间接健康特征优化与多模型融合的锂电池SOH-RUL联合预测[J].电工技术学报,2024, 39(18):5883–5898.CAI Y S, LI Z W, LIU P, et al. Joint prediction of lithium battery state of health and remaining useful life based on indirect health features optimization and multi-model fusion[J].Transactions of China Electrotechnical Society,2024, 39(18):5883–5898.(in Chinese)
[11]史永胜,翟欣然,栾飞,等.基于特征选择的lightGBM算法预测钠离子电池剩余寿命[J].陕西科技大学学报, 2024,42(2):174–181.SHI Y S, ZHAI X R, LUAN F, et al. Predicting remaining useful life of sodium-ion batteries using feature selection-based lightGBM algorithm[J]. Journal of Shaanxi University of Science&Technology, 2024, 42(2):174–181.(in Chinese)
[12]高明,刘超,唐加福,等.基于注意力神经网络的燃料电池寿命衰减预测[J].中国管理科学, 2023, 31(3):155–166.GAO M, LIU C, TANG J F, et al. Lifetime decay prediction of fuel cell based on attention neural network[J]. Chinese Journal of Management Science, 2023, 31(3):155–166.(in Chinese)
[13]章雷其,林沁,刘敏,等.质子交换膜燃料电池退化机制及寿命预测方法综述[J].洁净煤技术, 2024, 30(1):265–276.ZHANG L Q, LIN Q, LIU M, et al. Review of degradation mechanism and remaining useful life prediction of PEMFC[J].Clean Coal Technology, 2024, 30(1):265–276.(in Chinese)
[14]吴忠强,胡晓宇,马博岩,等.基于PF-LSTM的锂电池剩余使用寿命预测[J].计量学报, 2023, 44(6):939–947.WU Z Q, HU X Y, MA B Y, et al. Prediction of the remaining useful life of lithium-ion batteries based on PF-LSTM[J]. Acta Metrologica Sinica, 2023, 44(6):939–947.(in Chinese)
[15]柴兴华,王泽旭,杨建永,等.虚实融合的无人机集群仿真系统设计[J].实验技术与管理, 2024, 41(12):127–135.CHAI X H, WANG Z X, YANG J Y, et al. Design of virtual reality fusion UAV cluster simulation system[J]. Experimental Technology and Management, 2024, 41(12):127–135.(in Chinese)
[16]史永胜,翟欣然,胡玙珺.基于机器学习的钠离子电池剩余使用寿命预测[J].华南师范大学学报（自然科学版）, 2023,55(3):17–24.SHI Y S, ZHAI X R, HU Y J. Machine learning-based prediction of the remaining life of sodium-ion batteries[J].Journal of South China Normal University(Natural Science Edition), 2023, 55(3):17–24.(in Chinese)
[17]徐俊,郭喆晨,谢延敏,等.储能锂电池系统综合管理研究进展[J].西安交通大学学报, 2024, 58(10):1–23.XU J, GUO Z C, XIE Y M, et al. Review of research progress in integrated management for energy storage lithium battery systems[J]. Journal of Xi'an Jiaotong University, 2024, 58(10):1–23.(in Chinese)
[18]黄捷,李泽毅.四旋翼无人机编队变换能耗优化仿真教学[J].实验技术与管理, 2024, 41(4):102–108.HUANG J, LI Z Y. Simulated teaching for energy consumption optimization in quadcopter unmanned aerial vehicle formation change[J]. Experimental Technology and Management, 2024,41(4):102–108.(in Chinese)
[19]李杰,赵海波,李宗杰,等.基于Pearson系数与多元线性拟合的330 MV汽轮机高压汽缸轴向膨胀定量监测方法[J].汽轮机技术, 2024, 66(4):299–302.LI J, ZHAO H B, LI Z J, et al. high-pressure cylinder of 330 MV turbine based on pearson’s coefficient and multivariate linear fitting quantitative monitoring method for axial expansion[J].Turbine Technology, 2024, 66(4):299–302.(in Chinese)
Basic Information:
DOI：10.16791/j.cnki.sjg.2025.07.032
China Classification Code:G642.423;TM912-4
Citation Information:
[1]刘强,姜英姿,种法力等.虚实结合的电池剩余使用寿命预测实验教学研究[J].实验技术与管理,2025,42(07):246-252.DOI:10.16791/j.cnki.sjg.2025.07.032.
Fund Information:
CIQA首批(2024年)招标课题(CIQAJYD2024-YBKT-15-06); 江苏省高等学校自然科学研究重大项目(24KJA470006); 徐州工程学院服务地方重大培育项目(20240022); 江苏省高校实验室工作研究课题(GS2024YB15); 2025年大学生创新训练计划项目(XCX2025321)